© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 40975
    Prev
    Next
    INDEX
    Explanations

    absolute value |

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     “
    -1.92
     "
    -1.40
     (
    -1.27
    ﹠
    -1.27
    .<
    -1.27
    
    -1.21
    hiva
    -1.21
    \"",
    -1.20
     Vertrieb
    -1.18
     той
    -1.16
    POSITIVE LOGITS
     from
    1.95
     each
    1.66
     these
    1.53
    是怎么回事
    1.47
    並不是
    1.45
    細節
    1.43
     it
    1.40
    屢
    1.40
     дори
    1.38
     its
    1.36
    Activations Density 0.023%

    No Known Activations